Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2858 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4437. Min Act: -0.0000

Data Index: 806630 (The Pile)

Max Activating Token Index: 425

Text #1

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4338. Min Act: -0.0000

Data Index: 771822 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4150. Min Act: -0.0000

Data Index: 887515 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1437059 (The Pile)

Max Activating Token Index: 231

Text #4

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1601517 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3641. Min Act: -0.0000

Data Index: 552230 (The Pile)

Max Activating Token Index: 872

Text #6

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3274. Min Act: -0.0000

Data Index: 163602 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3524. Min Act: -0.0000

Data Index: 721218 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1559779 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3213. Min Act: -0.0000

Data Index: 797200 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1206560 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1275305 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2885. Min Act: -0.0000

Data Index: 481490 (The Pile)

Max Activating Token Index: 248

Text #13

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3025. Min Act: -0.0000

Data Index: 683567 (The Pile)

Max Activating Token Index: 39

Text #14

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3041. Min Act: -0.0000

Data Index: 336252 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1802671 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1661729 (The Pile)

Max Activating Token Index: 39

Text #17

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1365433 (The Pile)

Max Activating Token Index: 816

Text #18

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1834669 (The Pile)

Max Activating Token Index: 417

Text #19

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3048. Min Act: -0.0000

Data Index: 276281 (The Pile)

Max Activating Token Index: 567